Merge tag 'drm-intel-next-2020-08-24-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- Introduce a mechanism to extend execbuf2 (Lionel)
- Add syncobj timeline support (Lionel)

Driver Changes:

- Limit stolen mem usage on the compressed frame buffer (Ville)
- Some clean-up around display's cdclk (Ville)
- Some DDI changes for better DP link training according
  to spec (Imre)
- Provide the perf pmu.module (Chris)
- Remove dobious Valleyview PCI IDs (Alexei)
- Add new display power saving feature for gen12+ called
  HOBL (Jose)
- Move SKL's clock gating w/a to skl_init_clock_gating() (Ville)
- Rocket Lake display additions (Matt)
- Selftest: temporarily downgrade on severity of frequency
            scaling tests (Chris)
- Introduce a new display workaround for fixing FLR related
  issues on new PCH. (Jose)
- Temporarily disable FBC on TGL. It was the culprit of random
  underruns. (Uma).
- Copy default modparams to mock i915_device (Chris)
- Add compiler paranoia for checking HWSP values (Chris)
- Remove useless gen check before calling intel_rps_boost (Chris)
- Fix a null pointer dereference (Chris)
- Add a couple of missing i915_active_fini() (Chris)
- Update TGL display power's bw_buddy table according to
  update spec (Matt)
- Fix couple wrong return values (Tianjia)
- Selftest: Avoid passing random 0 into ilog2 (George)
- Many Tiger Lake display fixes and improvements for Type-C and
  DP compliance (Imre, Jose)
- Start the addition of PSR2 selective fetch (Jose)
- Update a few DMC and HuC firmware versions (Jose)
- Add gen11+ w/a to fix underuns (Matt)
- Fix cmd parser desc matching with mask (Mika)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826232733.GA129053@intel.com

6 files changed, 100 insertions, 52 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 24322ef08aa4..d03da2f64a49 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -4555,7 +4555,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
-		if (IS_KBL_REVID(request->engine->i915, 0, KBL_REVID_B0))
+		if (IS_KBL_GT_REVID(request->engine->i915, 0, KBL_REVID_B0))
 			dc_flush_wa = true;
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5726cd0a37e0..be5a4685c991 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -52,6 +52,24 @@
  * - Public functions to init or apply the given workaround type.
  */
 
+/*
+ * KBL revision ID ordering is bizarre; higher revision ID's map to lower
+ * steppings in some cases.  So rather than test against the revision ID
+ * directly, let's map that into our own range of increasing ID's that we
+ * can test against in a regular manner.
+ */
+
+const struct i915_rev_steppings kbl_revids[] = {
+	[0] = { .gt_stepping = KBL_REVID_A0, .disp_stepping = KBL_REVID_A0 },
+	[1] = { .gt_stepping = KBL_REVID_B0, .disp_stepping = KBL_REVID_B0 },
+	[2] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B0 },
+	[3] = { .gt_stepping = KBL_REVID_D0, .disp_stepping = KBL_REVID_B0 },
+	[4] = { .gt_stepping = KBL_REVID_F0, .disp_stepping = KBL_REVID_C0 },
+	[5] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B1 },
+	[6] = { .gt_stepping = KBL_REVID_D1, .disp_stepping = KBL_REVID_B1 },
+	[7] = { .gt_stepping = KBL_REVID_G0, .disp_stepping = KBL_REVID_C0 },
+};
+
 static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name)
 {
 	wal->name = name;
@@ -470,7 +488,7 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen9_ctx_workarounds_init(engine, wal);
 
 	/* WaToEnableHwFixForPushConstHWBug:kbl */
-	if (IS_KBL_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
+	if (IS_KBL_GT_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
 		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
 				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
@@ -596,8 +614,8 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
-static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
-				     struct i915_wa_list *wal)
+static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
+				       struct i915_wa_list *wal)
 {
 	/*
 	 * Wa_1409142259:tgl
@@ -607,12 +625,28 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	 * Wa_1409207793:tgl
 	 * Wa_1409178076:tgl
 	 * Wa_1408979724:tgl
+	 * Wa_14010443199:rkl
+	 * Wa_14010698770:rkl
 	 */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
+	/* WaDisableGPGPUMidThreadPreemption:gen12 */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
+}
+
+static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
+				     struct i915_wa_list *wal)
+{
+	gen12_ctx_workarounds_init(engine, wal);
+
 	/*
-	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * Wa_1604555607:tgl,rkl
+	 *
+	 * Note that the implementation of this workaround is further modified
+	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
 	 * FF_MODE2 register will return the wrong value when read. The default
 	 * value for this register is zero for all fields and there are no bit
 	 * masks. So instead of doing a RMW we should just write the GS Timer
@@ -623,11 +657,6 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	       FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224  | FF_MODE2_TDS_TIMER_128,
 	       0);
-
-	/* WaDisableGPGPUMidThreadPreemption:tgl */
-	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
-			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
-			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
 }
 
 static void
@@ -642,8 +671,10 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 
 	wa_init_start(wal, name, engine->name);
 
-	if (IS_GEN(i915, 12))
+	if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915))
 		tgl_ctx_workarounds_init(engine, wal);
+	else if (IS_GEN(i915, 12))
+		gen12_ctx_workarounds_init(engine, wal);
 	else if (IS_GEN(i915, 11))
 		icl_ctx_workarounds_init(engine, wal);
 	else if (IS_CANNONLAKE(i915))
@@ -995,7 +1026,7 @@ kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen9_gt_workarounds_init(i915, wal);
 
 	/* WaDisableDynamicCreditSharing:kbl */
-	if (IS_KBL_REVID(i915, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(i915, 0, KBL_REVID_B0))
 		wa_write_or(wal,
 			    GAMT_CHKN_BIT_REG,
 			    GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
@@ -1176,9 +1207,16 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 }
 
 static void
-tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+gen12_gt_workarounds_init(struct drm_i915_private *i915,
+			  struct i915_wa_list *wal)
 {
 	wa_init_mcr(i915, wal);
+}
+
+static void
+tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1409420604:tgl */
 	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0))
@@ -1196,8 +1234,10 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 static void
 gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
-	if (IS_GEN(i915, 12))
+	if (IS_TIGERLAKE(i915))
 		tgl_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 12))
+		gen12_gt_workarounds_init(i915, wal);
 	else if (IS_GEN(i915, 11))
 		icl_gt_workarounds_init(i915, wal);
 	else if (IS_CANNONLAKE(i915))
@@ -1630,18 +1670,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
 
 		/*
-		 * Wa_1607030317:tgl
-		 * Wa_1607186500:tgl
-		 * Wa_1607297627:tgl there is 3 entries for this WA on BSpec, 2
-		 * of then says it is fixed on B0 the other one says it is
-		 * permanent
-		 */
-		wa_masked_en(wal,
-			     GEN6_RC_SLEEP_PSMI_CONTROL,
-			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
-			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
-
-		/*
 		 * Wa_1606679103:tgl
 		 * (see also Wa_1606682166:icl)
 		 */
@@ -1654,22 +1682,17 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    VSUNIT_CLKGATE_DIS_TGL);
 	}
 
-	if (IS_TIGERLAKE(i915)) {
-		/* Wa_1606931601:tgl */
+	if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
+		/* Wa_1606931601:tgl,rkl */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ);
 
-		/* Wa_1409804808:tgl */
+		/* Wa_1409804808:tgl,rkl */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
 			     GEN12_PUSH_CONST_DEREF_HOLD_DIS);
 
-		/* Wa_1606700617:tgl */
-		wa_masked_en(wal,
-			     GEN9_CS_DEBUG_MODE1,
-			     FF_DOP_CLOCK_GATE_DISABLE);
-
 		/*
 		 * Wa_1409085225:tgl
-		 * Wa_14010229206:tgl
+		 * Wa_14010229206:tgl,rkl
 		 */
 		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
 
@@ -1677,9 +1700,29 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_1407928979:tgl A*
 		 * Wa_18011464164:tgl B0+
 		 * Wa_22010931296:tgl B0+
+		 * Wa_14010919138:rkl
 		 */
 		wa_write_or(wal, GEN7_FF_THREAD_MODE,
 			    GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
+
+		/*
+		 * Wa_1607030317:tgl
+		 * Wa_1607186500:tgl
+		 * Wa_1607297627:tgl,rkl there are multiple entries for this
+		 * WA in the BSpec; some indicate this is an A0-only WA,
+		 * others indicate it applies to all steppings.
+		 */
+		wa_masked_en(wal,
+			     GEN6_RC_SLEEP_PSMI_CONTROL,
+			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
+			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
+	}
+
+	if (IS_TIGERLAKE(i915)) {
+		/* Wa_1606700617:tgl */
+		wa_masked_en(wal,
+			     GEN9_CS_DEBUG_MODE1,
+			     FF_DOP_CLOCK_GATE_DISABLE);
 	}
 
 	if (IS_GEN(i915, 11)) {
@@ -1898,7 +1941,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	struct drm_i915_private *i915 = engine->i915;
 
 	/* WaKBLVECSSemaphoreWaitPoll:kbl */
-	if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
+	if (IS_KBL_GT_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
 		wa_write(wal,
 			 RING_SEMA_WAIT_POLL(engine->mmio_base),
 			 1);
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index 73243ba59c7d..e73854dd2fe0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -47,7 +47,10 @@ static int pulse_active(struct i915_active *active)
 
 static void pulse_free(struct kref *kref)
 {
-	kfree(container_of(kref, struct pulse, kref));
+	struct pulse *p = container_of(kref, typeof(*p), kref);
+
+	i915_active_fini(&p->active);
+	kfree(p);
 }
 
 static void pulse_put(struct pulse *p)
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 8624f5d2a1f3..34b403d47840 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -700,7 +700,7 @@ int live_rps_frequency_cs(void *arg)
 				f = act; /* may skip ahead [pcu granularity] */
 			}
 
-			err = -EINVAL;
+			err = -EINTR; /* ignore error, continue on with test */
 		}
 
 err_vma:
@@ -841,7 +841,7 @@ int live_rps_frequency_srm(void *arg)
 				f = act; /* may skip ahead [pcu granularity] */
 			}
 
-			err = -EINVAL;
+			err = -EINTR; /* ignore error, continue on with test */
 		}
 
 err_vma:
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index fb5b7d3498a6..6564c989dbee 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -491,7 +491,7 @@ checked_intel_timeline_create(struct intel_gt *gt)
 	if (IS_ERR(tl))
 		return tl;
 
-	if (*tl->hwsp_seqno != tl->seqno) {
+	if (READ_ONCE(*tl->hwsp_seqno) != tl->seqno) {
 		pr_err("Timeline created with incorrect breadcrumb, found %x, expected %x\n",
 		       *tl->hwsp_seqno, tl->seqno);
 		intel_timeline_put(tl);
@@ -561,9 +561,9 @@ static int live_hwsp_engine(void *arg)
 	for (n = 0; n < count; n++) {
 		struct intel_timeline *tl = timelines[n];
 
-		if (!err && *tl->hwsp_seqno != n) {
-			pr_err("Invalid seqno stored in timeline %lu @ %x, found 0x%x\n",
-			       n, tl->hwsp_offset, *tl->hwsp_seqno);
+		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
+			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
+				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -633,9 +633,9 @@ out:
 	for (n = 0; n < count; n++) {
 		struct intel_timeline *tl = timelines[n];
 
-		if (!err && *tl->hwsp_seqno != n) {
-			pr_err("Invalid seqno stored in timeline %lu @ %x, found 0x%x\n",
-			       n, tl->hwsp_offset, *tl->hwsp_seqno);
+		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
+			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
+				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -733,7 +733,8 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 
-		if (*hwsp_seqno[0] != seqno[0] || *hwsp_seqno[1] != seqno[1]) {
+		if (READ_ONCE(*hwsp_seqno[0]) != seqno[0] ||
+		    READ_ONCE(*hwsp_seqno[1]) != seqno[1]) {
 			pr_err("Bad timeline values: found (%x, %x), expected (%x, %x)\n",
 			       *hwsp_seqno[0], *hwsp_seqno[1],
 			       seqno[0], seqno[1]);
@@ -966,9 +967,10 @@ static int live_hwsp_recycle(void *arg)
 				break;
 			}
 
-			if (*tl->hwsp_seqno != count) {
-				pr_err("Invalid seqno stored in timeline %lu @ tl->hwsp_offset, found 0x%x\n",
-				       count, *tl->hwsp_seqno);
+			if (READ_ONCE(*tl->hwsp_seqno) != count) {
+				GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x found 0x%x\n",
+					      count, tl->fence_context,
+					      tl->hwsp_offset, *tl->hwsp_seqno);
 				GEM_TRACE_DUMP();
 				err = -EINVAL;
 			}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 59b27aba15c6..80e8b6c3bc8c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -51,8 +51,8 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * Note that RKL uses the same firmware as TGL.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
-	fw_def(ROCKETLAKE,  0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 12)) \
-	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 12)) \
+	fw_def(ROCKETLAKE,  0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 5, 0)) \
+	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 5, 0)) \
 	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9, 0, 0)) \
 	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  9, 0, 0)) \
 	fw_def(COMETLAKE,   5, guc_def(cml, 33, 0, 0), huc_def(cml,  4, 0, 0)) \